Download Bilibili subtitles in batch with resume support, skipping already downloaded files. Select text, SRT, or JSON output, and optionally fetch all video parts with automatic file suffixes.
批量下载字幕（断点续跑，已存在自动跳过）。all_parts=True 下载全部分 P； fmt: text/srt/json；output 为输出文件路径（all_parts 时自动加 .pN 后缀）。 长任务可能耗时数分钟；返回结构化进度事件与结果汇总。
| Name | Required | Description | Default |
|---|---|---|---|
| fmt | No | srt | |
| url | Yes | ||
| limit | No | ||
| output | Yes | ||
| all_parts | No |
Changes observed during successful MCP inspections.
v0.2.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden and does an excellent job: it discloses resume/breakpoint behavior, auto-skip for existing files, all_parts naming behavior, acceptable formats, output file suffix handling, potentially long duration, and structured progress/result returns. This goes well beyond minimal expectations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is compact and front-loaded with the most important behavioral differentiators first. Every sentence carries actionable information, and it avoids filler or redundant restating of the tool name.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description is strong for task selection and invocation basics, but with no output schema and no annotations, it leaves gaps: the 'structured progress events and result summary' format is not specified, and the limit parameter is left undocumented. More detail on limit or return shape would make it fully complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, so the description must compensate. It adds meaning for all_parts (downloads all parts, .pN suffix), fmt (text/srt/json), and output path semantics. It does not explain limit or url, but the majority of parameters are clarified.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action with a specific verb ('batch download subtitles') and resource, and adds key details like resuming and skipping existing files. However, it does not explicitly differentiate itself from the sibling tool get_video_subtitles, relying mainly on the word 'batch' for distinction.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Usage is implied through 'batch download' and the description of long-running behavior, but there is no explicit guidance about when to use this tool versus get_video_subtitles or another alternative. It does not state exclusions or conditions under which a sibling should be preferred.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.